Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

Modeling and Identifying Bottlenecks in the EOSDIS Architecture

Sharon L. Smith, Melody Y. Ivory and James Demmel

EECS Department
University of California, Berkeley
Technical Report No. UCB/CSD-97-957
September 1996

NASA's Earth Observing System (EOS) is a series of polar-orbiting and low-inclination satellites that will furnish global space-based measurements to advance scientific understanding of the entire Earth system, including hydrologic, biogeochemical, atmospheric, ecological, and geophysical processes. The EOS Data and Information system (EOSDIS) is a multi-million dollar hardware and software system that will enable scientists to access data generated by EOS. An EOSDIS architecture has been proposed to facilitate efficient organization and high performance retrieval of EOS data, however, the architecture needs to be examined to insure that EOSDIS will deliver adequate performance for anticipated workloads. To that end, we use performance modeling to identify bottlenecks in EOSDIS for two representative user scenarios from climate change research.


BibTeX citation:

@techreport{Smith:CSD-97-957,
    Author = {Smith, Sharon L. and Ivory, Melody Y. and Demmel, James},
    Title = {Modeling and Identifying Bottlenecks in the EOSDIS Architecture},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {1996},
    Month = {Sep},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/1996/5891.html},
    Number = {UCB/CSD-97-957},
    Abstract = {NASA's Earth Observing System (EOS) is a series of polar-orbiting and low-inclination satellites that will furnish global space-based measurements to advance scientific understanding of the entire Earth system, including hydrologic, biogeochemical, atmospheric, ecological, and geophysical processes. The EOS Data and Information system (EOSDIS) is a multi-million dollar hardware and software system that will enable scientists to access data generated by EOS. An EOSDIS architecture has been proposed to facilitate efficient organization and high performance retrieval of EOS data, however, the architecture needs to be examined to insure that EOSDIS will deliver adequate performance for anticipated workloads. To that end, we use performance modeling to identify bottlenecks in EOSDIS for two representative user scenarios from climate change research.}
}

EndNote citation:

%0 Report
%A Smith, Sharon L.
%A Ivory, Melody Y.
%A Demmel, James
%T Modeling and Identifying Bottlenecks in the EOSDIS Architecture
%I EECS Department, University of California, Berkeley
%D 1996
%@ UCB/CSD-97-957
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/1996/5891.html
%F Smith:CSD-97-957